Claude Skills by VersoXBT

Guide for creating MCP (Model Context Protocol) servers in TypeScript and Python, including scaffolding, transports, lifecycle hooks, and testing. Use when the user wants to build an MCP server, add tools/resources/prompts to an MCP server, configure stdio or SSE transport, or test MCP server functionality.

Best practices for designing MCP tools including naming conventions, input schemas, error responses, pagination, idempotency, and descriptions. Use when the user is designing tools for an MCP server, writing tool schemas, handling tool errors, or needs guidance on tool naming and input validation patterns.

Strategies for managing Claude Code's context window efficiently: token budgeting, progressive disclosure, reference files, and using subagents to protect context. Use when conversations are getting long, the user mentions context limits, or tasks involve reading many files.

Patterns for learning from corrections, capturing instincts, extracting stable patterns, and building cross-session knowledge. Use when the user corrects you, when you discover a recurring pattern, or when insights should persist beyond the current session.

Patterns for structuring MEMORY.md and topic-based memory files for Claude Code persistent memory. Use when the user asks about remembering things across sessions, wants to organize project knowledge, or needs guidance on what to save vs not save.

Implement effective caching at every layer: in-memory, Redis, CDN, and browser. Activate whenever the user asks about caching, performance optimization for repeated data access, Redis patterns, CDN configuration, cache invalidation, HTTP cache headers, memoization, or stale-while-revalidate strategies.

Implement lazy loading and code splitting to reduce initial bundle size and improve load times. Activate whenever the user works on bundle optimization, asks about code splitting, implements dynamic imports, uses React.lazy or Suspense, sets up route-based splitting, or optimizes image loading with intersection observer.

Profile and diagnose performance bottlenecks in web and backend applications. Activate whenever the user reports slow performance, asks about profiling tools, investigates memory leaks, needs to generate flame graphs, or is optimizing CPU or memory usage. Also activate when mentioning Chrome DevTools, cProfile, py-spy, pprof, or heap snapshots.

Structure Python projects with pyproject.toml, src layout, modern package managers (uv, rye, poetry), virtual environments, __init__.py, and namespace packages. Use when the user creates a new Python project, asks about project layout, configures packaging, sets up dependencies, or encounters import issues. Trigger when you see a Python project without proper structure.

Apply idiomatic Python patterns: list comprehensions, generators, context managers, decorators, dataclasses, walrus operator, and unpacking. Use when the user writes Python code, asks for Pythonic idioms, refactors Python, or mentions any of these patterns. Trigger proactively when you see non-idiomatic Python.

Guide Python type annotations using the typing module: Protocol, TypeVar, ParamSpec, Generic, Literal, TypeAlias, overload, and dataclass field typing. Use when the user writes Python type hints, asks about typing, creates generic classes, defines protocols, or works with mypy/pyright. Trigger when you see untyped Python code that should be typed.

React component composition patterns including compound components, render props, HOCs, and controlled vs uncontrolled components. Use when the user is building React components, asking about component architecture, refactoring components, or designing reusable UI APIs. Trigger on mentions of compound components, render props, higher-order components, forwardRef, composition, or component design patterns.

Advanced React hooks patterns including custom hooks, memoization, refs, reducers, and external store synchronization. Use when the user is writing custom hooks, optimizing React performance with useCallback/useMemo, managing complex state with useReducer, or integrating external state stores. Trigger on any mention of React hooks, custom hooks, memoization, re-render optimization, or rules of hooks violations.

Next.js App Router patterns including server components, route handlers, middleware, parallel routes, intercepting routes, streaming, and caching strategies. Use when the user is building with Next.js 13+/14+/15+, asking about the App Router, server components vs client components, route handlers, Next.js middleware, or Next.js caching and revalidation. Trigger on any mention of Next.js, App Router, server components, or Next.js API routes.

Manage Rust projects effectively with Cargo workspaces, features, and tooling. Use when the user sets up Cargo workspaces, configures feature flags, writes build.rs scripts, prepares crates for publishing, or uses cargo clippy, cargo fmt, and other Cargo development tools.

Implement idiomatic Rust error handling with Result, Option, and the ? operator. Use when the user handles errors in Rust, creates custom error types, uses thiserror or anyhow, implements the From trait for error conversion, or asks about Result/Option patterns and error composition strategies.

Master Rust's ownership, borrowing, and lifetime system for memory-safe code. Use when the user encounters borrow checker errors, lifetime annotations, needs smart pointers (Box/Rc/Arc), works with move semantics, or asks about Clone vs Copy, ownership transfer, and reference management in Rust.

Validate and sanitize all user input using schema validation libraries. Activate whenever the user writes form handlers, API endpoints, request parsers, data processing functions, or any code that accepts external input. Also activate when the user asks about validation libraries like Zod, Joi, or Pydantic, or discusses input sanitization.

Prevent OWASP Top 10 vulnerabilities in web applications. Activate whenever the user writes API endpoints, form handlers, database queries, authentication logic, file uploads, HTML rendering, or any code that handles user input or external data. Also activate when the user asks about security, hardening, or vulnerability prevention.

Manage secrets, API keys, and sensitive configuration securely. Activate whenever the user handles API keys, passwords, tokens, database credentials, .env files, CI/CD pipelines, or any configuration that contains sensitive values. Also activate when the user asks about secret rotation, vault integration, or gitignore setup.

Mocks vs stubs vs spies, dependency injection for testing, jest.mock/unittest.mock/gomock, and when NOT to mock. Use when the user needs to isolate dependencies in tests, asks about mocking external services, or has tests tightly coupled to implementation details.

Red-green-refactor TDD cycle, test-first methodology, coverage targets (80%+), and test pyramid. Use when the user is implementing a new feature, fixing a bug, asks about TDD, or mentions writing tests before code. Always push for test-first.

Test organization, fixtures, factories (factory_boy/faker), test isolation, database cleanup, and test configuration. Use when the user is setting up a test suite, organizing test files, creating test fixtures, or dealing with test isolation issues.

Master TypeScript generics for reusable, type-safe abstractions. Use when the user works with generic constraints, conditional types, mapped types, the infer keyword, utility types, recursive types, or needs help building type-safe libraries, APIs, or data structures.

Enforce strict TypeScript compiler settings and type narrowing patterns. Use when the user creates a new TypeScript project, configures tsconfig.json, encounters null/undefined errors, deals with indexed access issues, or asks about strict mode, type safety, or narrowing techniques.

Advanced TypeScript type patterns for modeling complex domains safely. Use when the user needs discriminated unions, branded types, template literal types, type guards, exhaustive checking, const assertions, or is designing type-safe APIs and domain models.